Fix runtime issues

Fix thinking quote

Update default template

fix gpu time estimating

Generalize thinking

Change model selection

Update UI

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Add model switching interruption and support for reasoning model tokens (#4)

Update app.py

Update README.md

Update app.py

Update app.py (#3)

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Add token generating stat

Update app.py

Increase inference wait timeout

Update requirements.txt

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Create requirements.txt

Create app.py

initial commit